Method and system for emissions-based asset integrity monitoring and maintenance

Abstract

A method involves obtaining current asset data for an asset, the current asset data including process data. The method further involves predicting, using a machine learning model, a methane emissions event associated with the asset, based on the current asset data, and reporting the predicted methane emissions event in a user visualization.

What is claimed: 
     
         1 . A method, comprising:
 obtaining current asset data for an asset, the current asset data comprising process data;   predicting, using a machine learning model, a methane emissions event associated with the asset, based on the current asset data; and   reporting the predicted methane emissions event in a user visualization.   
     
     
         2 . The method of  claim 1 , wherein the asset comprises at least one petrochemical asset. 
     
     
         3 . The method of  claim 1 , wherein the current asset data further comprises at least one selected from a group consisting of:
 environmental data,   historical data associated with the asset, and   methane sensor data.   
     
     
         4 . The method of  claim 1 , wherein the prediction of the methane emissions event comprises a classification performed between multiple categories of methane emissions events of different magnitude. 
     
     
         5 . The method of  claim 1 , wherein the prediction of the methane emissions event comprises a prediction of at least one selected from a group consisting of a timing, a location, and a quantification of the methane emissions event. 
     
     
         6 . The method of  claim 1 , further comprising:
 predicting, using the machine learning model, a mitigation action for the methane emissions event.   
     
     
         7 . The method of  claim 6 , wherein the mitigation action comprises adjusting a setting of a valve associated with the asset. 
     
     
         8 . The method of  claim 6 , further comprising:
 performing the mitigation action such that an actual occurrence of the predicted methane emissions event is avoided.   
     
     
         9 . The method of  claim 1 , further comprising, prior to performing the prediction:
 obtaining, for the asset, archived asset data comprising process data and methane sensor data; and   training the machine learning model to predict methane emissions events based on the archived asset data used as training data.   
     
     
         10 . The method of  claim 9 , further comprising, prior to training the machine learning model:
 preprocessing the archived asset data, comprising at least one selected from a group consisting of removing outliers and removing false positives.   
     
     
         11 . The method of  claim 9 , further comprising, prior to training the machine learning model:
 standardizing the archived asset data for sensor-agnostic operation of the machine learning model.   
     
     
         12 . A system, comprising:
 a computing environment that:
 obtains current asset data for an asset, the current asset data comprising process data, 
 predicts, using a machine learning model, a methane emissions event associated with the asset, based on the current asset data; and 
   a dashboard comprising a user visualization that reports the predicted methane emissions event.   
     
     
         13 . The system of  claim 12 , wherein the machine learning model is a digital twin that establishes a virtual model that reflects characteristics of a physical environment related to the methane emissions event. 
     
     
         14 . The system of  claim 13 ,
 wherein the asset is in the physical environment reflected by the virtual model, and   wherein the asset is one selected from a group consisting of a vapor recovery unit, a compressor, storage tank, a power unit, a valve, a flange, and a seal.   
     
     
         15 . The system of  claim 14 , wherein the physical environment comprises sensors that obtain the current asset data for the asset in the physical environment. 
     
     
         16 . The system of  claim 15 , wherein the sensors comprise at least one selected from a group consisting of a fenceline sensor, a thermal camera, a non-thermal camera, an optical gas imaging camera, a drone-based sensor, a robot-based sensor, a helicopter-based sensor, an airplane-based sensor, and a satellite-based sensor. 
     
     
         17 . The system of  claim 15 ,
 wherein the computing environment comprises an edge computing platform that receives the current asset data from the sensors, and forwards the current asset data to the digital twin.   
     
     
         18 . The system of  claim 13 ,
 wherein the computing environment comprises a cloud computing platform, and   wherein the digital twin is executed on the cloud computing platform.   
     
     
         19 . The system of  claim 13 ,
 wherein the computing environment comprises a supervisor control and data acquisition (SCADA) system that obtains the process data associated with the asset and forwards the process data to the digital twin.   
     
     
         20 . The system of  claim 12 ,
 wherein the user visualization in the dashboard is configurable to enable monitoring of the methane emissions on a global, regional, side-wide, and asset-specific level.